skills/agentmark-ai/skills/agentmark/Gen Agent Trust Hub

agentmark

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes frequent use of the agentmark CLI via npx to perform project operations such as running experiments, generating types, and managing deployments. These operations utilize the vendor's specialized tooling.\n- [EXTERNAL_DOWNLOADS]: The skill is configured to fetch documentation and metadata from docs.agentmark.co (e.g., llms.txt, mcp server reference). These are trusted official sources for the AgentMark ecosystem.\n- [DATA_EXFILTRATION]: The skill provides instructions for linking local projects to AgentMark Cloud (app.agentmark.co), which involves the legitimate transmission of local traces and telemetry for observability and management purposes as part of the tool's core functionality.\n- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process content from .prompt.mdx and .jsonl files, which may contain untrusted data.\n
  • Ingestion points: Dataset rows in .jsonl files and prompt templates in .prompt.mdx files (specifically workflows/building-datasets.md and workflows/creating-prompts.md).\n
  • Boundary markers: Employs TemplateDX tags (e.g., <System>, <User>, <Assistant>) to provide structure and separation between instruction blocks, though it relies on correctly defined schemas to mitigate malicious property injection.\n
  • Capability inventory: The agent is empowered to execute CLI commands (npx agentmark), conduct network operations to cloud endpoints, and modify local project files.\n
  • Sanitization: Relies on frontmatter-defined JSON Schemas for input validation as described in workflows/creating-prompts.md.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 12:10 PM
Security Audit — agent-trust-hub — agentmark